Leo
@arogozhnikov, I see. Thanks for the reply!
Ran into the same issue. I'm inclined to think this might be a problem due to vanishing gradients, especially because you guys mentioned that playing with epochs or normalization appeared...
The fix should be relatively straightforward: ```python @dataclass class MaxxVitCfg: embed_dim: Tuple[int, ...] = (96, 192, 384, 768) depths: Tuple[int, ...] = (2, 3, 5, 2) block_type: Tuple[Union[str, Tuple[str, ...]],...
I came here to post an issue about this idea. Seems you guys are already on track. What I had in mind is Whisper and a lot of podcast content...
@yk, please move this into backlog with the relevant labels and everything if you consider it useful.
@SkanderHellal, I'm not that concerned about performance. I'm more concerned about how we store the data. A classical data structure is an [AST](https://www.wikiwand.com/en/Abstract_syntax_tree). However, it's not at all clear how...
Open issue for me as well. Error reported is: `Static content: index.html of watcher: aw-watcher-input not found!`. I did follow all the steps as described in the `README.md`. Posting more...
### Update I messed up the config. After the correction, it works. Posting it here for tracking: ``` [server] host = "localhost" port = "5600" storage = "peewee" cors_origins =...
+, I have the same issue for version 0.2.82
> > +, I have the same issue for version 0.2.82 > > Check your prompt template I suppose that the llama-cpp-python server should mirror the llama-cpp server, which works...